 Ensinnä yleisesti kannattaa käyttää ratkaisuja eri perustajia. Otetaan laittaa yksi esimerkki, jota olen käyttänyt. Ennen on tällaista ns. talouselmaa. Jälkeen puhutaan 500-lämmästä talouselmaa. Pitäнегоisellció on 500 eri huoneen kaikkiaan. Työn funktuja löytyvät ovat ilman yksilöitä, mitä he Targeti heitettäivät tullut vuoden vuosin. Joten se on followed by many reporters and many people who follow generally the Finnish business environment. In 2005 there was a big headline in one of the most prestigious Finnish newspapers that on this list the women's companies had 4.7% points higher return on assets than those companies whose CEO was a man. So what can we say based on this fact, we have a 4.7% point difference which is pretty substantial on one variable. Based difference between two groups. So the most obvious claim that people want to make with this kind of number is that naming a woman as a CEO causes the profitability to increase. So we have a claim with all kinds of policy implications. But that's not the only claim and it may not be the valid claim that we can make from this fact, this number. So to understand what kind of claims we can make generally, let's take a look at three purposes of statistics. The first purpose, the most simple one is description. So we can just say that women's companies are more profitable now or in 2005 and we don't even try to generalize anywhere. So we just state a fact and that kind of description could be useful. For example if one third of students taking a research methods course fail, then that provides an indication that there is either something wrong with the students or something wrong with the course even if we don't try to make any stronger claims. Then the second level of sophistication in statistical analysis is prediction. So the predictive claim would be that if a company is led by a woman, then it will be more profitable. So that's not a causal claim. So it's not a claim that the woman is actually the cause of the profitability difference. It is a claim that if we observe a women company, then for some reason it is likely to be more profitable. And prediction is useful for example if we know that if a company is led by a woman, then it will be more profitable. If we know that and others don't, we could make investment decisions that are better than other investors for example. Predictive analytics is very useful, we do forecasting and predictions all the time. You watch weather forecast, you banks forecast or predict who is going to pay their mortgage on time, who is going to be late, and stock market or investors try to forecast where the stock market goes and so on. So prediction without any claims about causality is very useful, but that's not very common in quantitative research. Then we have the third step which is a causal inference. So naming a woman as a CEO causes the company to be more profitable. So here we attribute the difference. We are not saying that this is merely a correlation relationship. We attribute the difference in the return on assets to women being CEOs of some companies and not others. And this has clear policy implications. If you have a male CEO, then you could increase your profitability by naming a woman CEO if this claim is true. Then we have still a fourth level of claims that we can make which goes beyond statistics. And that is a causal explanation. So a causal explanation differs from a causal inference in that we don't only make a claim that it's a woman that causes the company to be more profitable, but we also explain why that is the case. So that's why it's a causal explanation. Typically quantitative analysis can get us to the causal inference part, but the explanation needs to come from somewhere else. So we don't generally get to make theory from numbers. We only can make test claims.