WEBVTT WEBVTT Kind: captions Language: en 00:00:00.030 --> 00:00:05.460 Measurement is an important part of social science  research. If we take a look at this research   00:00:05.460 --> 00:00:11.700 process diagram from single demonstrates we can  see that the two most important decisions after   00:00:11.700 --> 00:00:18.420 you have decided on your research question is what  do you sample, what are the units of analysis and   00:00:18.420 --> 00:00:25.590 what do you measure which means are the variables  that you study from those units of analysis. 00:00:25.590 --> 00:00:31.320 After that you make your data collection and you  do your data analysis and report the results. 00:00:31.320 --> 00:00:39.330 The important part is that the quality of  your study is mostly determined by what do   00:00:39.330 --> 00:00:43.680 you sample and what do you measure from  your sample. So when you have your data   00:00:43.680 --> 00:00:49.560 then the upper limit of the quality  of the study is basically determined 00:00:49.560 --> 00:00:54.930 If your measurement doesn't work or  if your sample is somehow flawed then   00:00:54.930 --> 00:00:59.160 no matter how complicated or how  sophisticated analysis you apply   00:00:59.160 --> 00:01:03.900 to those poor data your research  output will not be very high. 00:01:03.900 --> 00:01:10.020 The idea of measurement is that we want  to assign numbers to some quantities that   00:01:10.020 --> 00:01:16.350 we study. For example some things that  we could study are heights of people,   00:01:16.350 --> 00:01:22.170 temperature outside, intelligence of  a person, innovativeness of company. 00:01:22.170 --> 00:01:27.120 The idea of all these quantities is  that they are variables. The idea   00:01:27.120 --> 00:01:31.530 that something is a variable means that  it varies. Some people are taller than   00:01:31.530 --> 00:01:36.960 others. Sometimes it's colder outside.  Sometimes it's warmer outside. Sometimes   00:01:36.960 --> 00:01:40.710 some people are smarter than others. Some  companies are more innovative than others. 00:01:40.710 --> 00:01:45.870 So the idea is that there's some  kind of variation in the objects   00:01:45.870 --> 00:01:49.830 or the units that you study and  the idea of measurement is that   00:01:49.830 --> 00:01:56.130 you want to assign some numbers to that  variation to quantify that variation. 00:01:56.130 --> 00:02:03.360 There are three key questions when you do  measurement. The first question is where do   00:02:03.360 --> 00:02:11.220 you get the numbers? So how do we assign the  height of a person? We can't quantify it. So   00:02:11.220 --> 00:02:17.520 for height that's obvious we use a measurement  tape for example. For temperature you use a   00:02:17.520 --> 00:02:22.530 thermometer but there are different kinds  of thermometers that you can apply also. 00:02:22.530 --> 00:02:29.160 But how do you quantify things that are not  physical quantities like innovativeness or   00:02:29.160 --> 00:02:34.380 intelligence? That's a less straightforward to  do and there are different ways of doing it. 00:02:34.380 --> 00:02:39.990 The next question is what does the number  tell you? So if you say that a company's   00:02:39.990 --> 00:02:45.270 innovativeness is 5. Is it a lot or  a little? What does it actually mean?   00:02:45.270 --> 00:02:50.520 So we're talking about the meaning of the  number and the interpretation of the number. 00:02:50.520 --> 00:02:55.920 Finally how do we justify the way we  assign the numbers? So we of course   00:02:55.920 --> 00:03:01.140 are besides just getting the numbers we  have to convince our readers and ourselves   00:03:01.140 --> 00:03:05.850 that our numbers are actually valid for  the purpose that we're using them for. 00:03:05.850 --> 00:03:12.720 There are a couple of different like  higher-level ways of getting the numbers.   00:03:12.720 --> 00:03:19.020 Let's look at the research designs by Singleton  and Straits. They present four research designs. 00:03:19.020 --> 00:03:22.770 The first is a laboratory experiment. The idea of   00:03:22.770 --> 00:03:28.080 laboratory experiment is that you don't  actually measure the key variable that   00:03:28.080 --> 00:03:34.020 you're studying instead you manipulate it.  So laboratory experiments and experimental   00:03:34.020 --> 00:03:38.250 studies are more about manipulation  of things than measurement of things. 00:03:38.250 --> 00:03:42.150 The remaining three are about measurement and they   00:03:42.150 --> 00:03:47.070 are different approaches of measurement  and to some extent sampling as well. 00:03:47.070 --> 00:03:52.410 The idea of a survey is that you  measure things by asking people.   00:03:52.410 --> 00:03:58.140 So the subjects are provided the numbers.  If we study people, their intelligence,   00:03:58.140 --> 00:04:03.780 then we ask them whether they're smart  or not. And if we study companies we   00:04:03.780 --> 00:04:07.020 ask people in those companies whether  the companies are innovative or not. 00:04:07.020 --> 00:04:12.990 We can do it also indirectly by asking whether  the companies have been successful in producing   00:04:12.990 --> 00:04:17.820 new products and new services and then we  have the second category field research. 00:04:17.820 --> 00:04:22.080 The idea of field research is that we  don't ask the subjects instead we rate   00:04:22.080 --> 00:04:29.370 or our research assistant rates or  evaluates the subjects and records   00:04:29.370 --> 00:04:33.270 what happens based on observation  and that gives us the numbers. 00:04:33.270 --> 00:04:39.210 Finally we can use numbers collected by  others so that's the archival records. 00:04:39.210 --> 00:04:46.290 So that's basically how we get the numbers.  The actual practicalities of how they do that   00:04:46.290 --> 00:04:50.880 is something that I'll address in other  video but those are the three main main   00:04:50.880 --> 00:04:56.850 ways of getting the numbers. Ask the people rate  yourself. Use data collected by somebody else. 00:04:56.850 --> 00:05:05.640 The next question is what the numbers tell  us and how do we justify the numbers? To   00:05:05.640 --> 00:05:10.620 answer those questions we need to understand  a little bit about measurement theory which   00:05:10.620 --> 00:05:15.570 relates to how the data and the  thing being measured are related. 00:05:15.570 --> 00:05:20.700 To understand measurement theory we need  to understand the concepts of a latent   00:05:20.700 --> 00:05:26.070 variable. The idea of a latent variable  is that an observed variable is that we   00:05:26.070 --> 00:05:32.100 have two types of variables. The observed  variables are variables for which we have   00:05:32.100 --> 00:05:38.250 case values. So we have a specific number  for each individual in our sample. We have   00:05:38.250 --> 00:05:42.600 a specific number for innovativeness of the  first company's the second company and so on. 00:05:42.600 --> 00:05:49.530 These are in moral path diagrams. These  are presented by these squares. Sometimes   00:05:49.530 --> 00:05:54.930 measurement measured variables are called  indicators or manifest variables which   00:05:54.930 --> 00:05:59.430 highlight that their purpose of these  measured variables is oftentimes to   00:05:59.430 --> 00:06:03.300 quantify some unmeasurable or unobservable thing. 00:06:03.300 --> 00:06:10.230 Latent variable is another kind of variable.  The idea of latent variable is simply that it   00:06:10.230 --> 00:06:14.520 is a variable for which we don't have the  case value. So we know that there is some   00:06:14.520 --> 00:06:20.850 variation between companies or between  people but we cannot specifically assign   00:06:20.850 --> 00:06:24.450 numbers to any companies. We just  know that there's some variation on   00:06:24.450 --> 00:06:29.190 some attribute or some variable but  we cannot assign the exact numbers. 00:06:29.190 --> 00:06:34.410 We can estimate these numbers and we  can estimate correlations within latent   00:06:34.410 --> 00:06:39.870 variables so we can't say what the specific  values are. So the difference between latent   00:06:39.870 --> 00:06:46.140 variable and observed variable are important  when we talk about measurement theory and when   00:06:46.140 --> 00:06:53.970 we talk about models that allow us to test or  use or operationalize our measurement theory. 00:06:55.050 --> 00:06:58.080 Then we need to understand a couple  of other terms as well. We have to   00:06:58.080 --> 00:07:01.230 understand the difference between  concept construct and measure. 00:07:01.230 --> 00:07:10.710 The idea of a concept is that it's an abstract  label for things that we study. And concepts have   00:07:10.710 --> 00:07:17.820 a reference and often the meaning as well. The  idea of a reference is that for example if we have   00:07:17.820 --> 00:07:25.800 a concept of rock that refers to certain objects  that we call rocks. The idea of meaning is that   00:07:25.800 --> 00:07:31.680 the concept has some kind of meaning as well. So  if if we say that we have a rock then people know   00:07:31.680 --> 00:07:38.940 that well we have something that is a naturally  occurring. It is a hard object. It's probably size   00:07:38.940 --> 00:07:45.240 of a couple of fists or so. That's it instead  of a boulder which is a larger one and so on. 00:07:45.240 --> 00:07:49.650 So the term has some kind of  attributes or the concept has   00:07:49.650 --> 00:07:54.630 some kind of attributes that are attached  to it that give it meaning. Then a concept   00:07:54.630 --> 00:07:59.190 can also have a definition and the idea  of a definition is that we have agreed   00:07:59.190 --> 00:08:06.000 on a specific written definition  of what exactly the concept means. 00:08:06.000 --> 00:08:12.780 When you read papers that develop theory  or introduce new constructs then they quite   00:08:12.780 --> 00:08:18.420 often define the construct explicitly.  I'll get your constructs in a moment. 00:08:18.420 --> 00:08:24.960 Examples of concepts are persons for  example and rocks and many other things.   00:08:24.960 --> 00:08:29.940 So concepts are like abstractions of  things that we can observe and study. 00:08:29.940 --> 00:08:38.100 Construct is a special kind of a concept. It  is a conceptual variable. So the idea is that   00:08:38.100 --> 00:08:45.510 it can vary so people or organizations can have  different decrease of the cone structure. You   00:08:45.510 --> 00:08:51.330 can have a different decrease of innovativeness  different amounts of intelligence and so on. 00:08:51.330 --> 00:08:56.790 So whereas in these concepts they can  refer generally to just about anything,   00:08:56.790 --> 00:09:03.480 construct is something that is typically  quantifiable. And the reason that these are   00:09:03.480 --> 00:09:08.610 because these are quantifiable we can study  constructs using quantitative techniques. 00:09:08.610 --> 00:09:17.760 Constructs are also latent in the meaning that  we cannot assign explicit correct values. We   00:09:17.760 --> 00:09:22.950 can only observe constructs indirectly.  Constructs also can have dimensions for   00:09:22.950 --> 00:09:28.230 example we could have a construct of a person's  size with the two main dimensions of height and   00:09:28.230 --> 00:09:35.130 weight of the person. Then some examples are  intelligence. It could have some dimensions.   00:09:35.130 --> 00:09:41.970 Innovativeness it could have dimensions. So  for example how well you are doing in product   00:09:41.970 --> 00:09:46.290 innovation and how well you are doing a  service or process innovation and so on. 00:09:46.290 --> 00:09:53.760 Then measure is the third kind of on variable or  a thing that you need to understand. Measure is an   00:09:53.760 --> 00:10:01.740 observable variable that quantifies one dimension  of construct. If you have multiple dimensions in a   00:10:01.740 --> 00:10:07.920 construct then you need one at least one measure  for each. So it doesn't make any sense to try to   00:10:07.920 --> 00:10:12.630 quantify person size using one number. You need  at least two numbers: the height and weight. 00:10:12.630 --> 00:10:18.510 Examples include IQ test scores so  that a measure for intelligence and   00:10:18.510 --> 00:10:23.400 reading on mercury column thermometer  which is a measure of our temperature. 00:10:23.400 --> 00:10:31.380 How do these construction measures then  relate? There are two main approaches. 00:10:31.380 --> 00:10:38.970 One is a nominalism. The idea is that  in nominalism you basically reject the   00:10:38.970 --> 00:10:45.360 existence of constructs independently  of measurement. An extreme version of   00:10:45.360 --> 00:10:52.890 nominalism is operationalism which says  that the construct is simply whatever the   00:10:52.890 --> 00:10:57.630 measurement process produces. So the  construct is defined by the measure. 00:10:57.630 --> 00:11:05.880 And then realism assumes that the constructs exist  independently of measurement and the purpose of   00:11:05.880 --> 00:11:13.020 measurement is to discover the true values of the  construct. Most social science research follows   00:11:13.020 --> 00:11:18.840 the realist approach. So the idea is that  there exists something called innovativeness   00:11:18.840 --> 00:11:24.510 independently of our measurement. Some we can  say that some companies are more innovative   00:11:24.510 --> 00:11:30.660 than others without measuring those. So that  kind of statements make sense if we assume   00:11:30.660 --> 00:11:37.770 that innovativeness or intelligence exist  independently of our measurement attempts. 00:11:37.770 --> 00:11:47.190 Then how we actually apply these concepts  in practices is that we use the measures as   00:11:47.190 --> 00:11:54.330 proxies for the constructs. We cannot really  observe the constructs directly so the next   00:11:54.330 --> 00:12:01.590 best best thing is that we build some kind of  statistical presentation based on our data.   00:12:01.590 --> 00:12:08.700 And for example or we can just use a number as  such, we can take a sum of multiple numbers or   00:12:08.700 --> 00:12:16.230 we can build a latent variable model and then use  the latent variable as a proxy for the construct. 00:12:16.230 --> 00:12:23.010 So we use these empirical representations  constructed based on our data as proxies   00:12:23.010 --> 00:12:30.570 for the constructs assuming that the  implicit representation is a perfect   00:12:30.570 --> 00:12:35.340 representation of the construct. That is  of course something that is a hardly ever   00:12:35.340 --> 00:12:39.600 exactly correct but we have to justify  that it is a good enough approximation. 00:12:39.600 --> 00:12:44.610 So that's the idea of a proxy. Instead  of using the construct when we study   00:12:44.610 --> 00:12:48.840 something we use the measure as  a stand-in for the construct. 00:12:48.840 --> 00:12:57.450 Summary of these key concepts. We have the  constructs. Construct is a concept so it's   00:12:57.450 --> 00:13:02.610 a variable that exists in principle.  It can have some definition. Almost   00:13:03.120 --> 00:13:10.080 always has a definition. We can say that  some companies or some individuals are   00:13:10.080 --> 00:13:14.610 higher on the construct than others  and we cannot observe it directly. 00:13:14.610 --> 00:13:22.500 Then observable variables are specific numbers  for each subject or a case that we have collected   00:13:22.500 --> 00:13:30.360 somehow. The idea is that these measures are  - if we take the realist perspective - the   00:13:30.360 --> 00:13:37.170 idea is that the variation in these measures  is caused by the variation in the construct.   00:13:37.170 --> 00:13:44.910 For example our people's IQ score differs  because their intelligence differs. So the   00:13:44.910 --> 00:13:50.130 reason why there's variation in the data is that  there's variation in the construct. Thermometer   00:13:50.130 --> 00:13:56.550 changes its value because the temperature  outside is different from one day to another. 00:13:56.550 --> 00:14:03.090 So that's the idea of realist perspective to  measurement which I will be using in these videos.